© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39257
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICC
    -0.29
    _DOM
    -0.28
    -dom
    -0.27
    ALAR
    -0.27
    CFG
    -0.26
    线ä¸ĭ
    -0.26
    åIJĮæĦı
    -0.25
     dom
    -0.25
    OSH
    -0.25
    elon
    -0.24
    POSITIVE LOGITS
    èĥĿ
    0.35
    @Module
    0.28
    æķĪ
    0.27
    horia
    0.27
    åĪ°ä½į
    0.27
    abin
    0.26
    ->__
    0.25
    åĪ¶åº¦æĶ¹éĿ©
    0.25
    sequences
    0.24
    åIJijä¸Ĭ
    0.24
    Activations Density 0.053%

    No Known Activations

    This feature has no known activations.